JP2020191043A - Abnormality detector, abnormality detection server, and abnormality detection method - Google Patents

Abstract

To provide an abnormality detector for detecting processing abnormality of a machine tool.SOLUTION: An abnormality detector 2 includes: a processing state collection part 211 which collects processing execution information at predetermined time intervals; a processing execution information recording part 212 which records the collected processing execution information into a recording part 22; a selection part 213 which executes a processing command a plurality of times and thereby selects, from a set of a plurality of pieces of recorded processing execution information, a subset of the processing execution information in order to calculate an average pattern corresponding to a processing step to be analyzed; an average pattern calculation part 214 which calculates, based on the subset, the average pattern corresponding to the processing step to be analyzed: and an abnormality detection part 215 which compares the processing execution information of the processing step to be analyzed with the average pattern and detects the presence or absence of abnormality occurring in the processing step to be analyzed.SELECTED DRAWING: Figure 1

Description

The present invention relates to an abnormality detection device, an abnormality detection server, and an abnormality detection method.

Conventionally, it is often the case that the machining load suddenly increases or decreases during machining even during normal machining. Therefore, it is difficult to determine whether or not the machining is abnormal only by displaying the machining load during machining.
The control device monitors, for example, the machining load torque, outputs an alarm when the machining load exceeds a certain level, or when the difference between the machining load and the reference data exceeds a certain level, and interrupts the machining. Or, it is known that the cutting feed speed is reduced to reduce the load.
By doing so, damage to the tool is prevented and processing defects of the workpiece are prevented.
In order to carry out such a machining load monitoring method, a trial cutting of the work is performed in advance, and the machining load data in the trial cutting is collected as sampling data at regular intervals, and then at the time of actual cutting, A machining load monitoring method is known in which the reference data, which is the sampling data, and the actual measurement data are compared at regular intervals to monitor the machining load.
In the conventional machining load monitoring method described above, the machining load at each trial cutting, which is sampling data, may change due to various factors such as tools, workpiece variations, cutting oil, etc. at the time of the trial cutting. high. Therefore, when the reference data is obtained by one trial cutting, the reference data does not always represent the accurate machining load in the cutting, and therefore, due to the variation of the reference data for monitoring the machining load. , There may be cases where accurate judgment cannot be made.

In this regard, Patent Document 1 describes, in a machining load monitoring method for monitoring the machining load of a machine tool, the reference data of the machining load is obtained by an average value from the sampling data of the machining load of a plurality of times at the time of trial cutting, and the data thereof Obtain the variance, set a threshold according to the variation of the sampling data using the value of the variance, compare the reference data and the measured data of the machining load at regular intervals, and check whether the difference exceeds the threshold. A machining load monitoring method for monitoring a machining load by detecting the above is disclosed.
In the machining load monitoring method disclosed in Patent Document 1, a monitoring method for monitoring the machining load during actual cutting is adopted based on the reference data of the machining load obtained from the sampling data of the machining load multiple times during trial cutting. Will be done. That is, when the same cutting process is repeatedly performed on a plurality of workpieces, the processing load at the time of each cutting process is compared with the same reference data.
However, when the same cutting process is repeatedly performed on a plurality of workpieces, the state of the machine tool when the first workpiece is machined (for example, the wear state of the tool) and the next state after the repeated cutting process are performed. It is presumed that the state of the machine tool when cutting the work is not necessarily the same. Then, the reference data disclosed in Patent Document 1 is suitable for comparison with the actual measurement data obtained when cutting the first workpiece, for example, but after the repeated cutting, the next It may not always be suitable for comparison with actual measurement data obtained when cutting a workpiece.
Further, in the machining load monitoring method disclosed in Patent Document 1, for example, when it is detected that the machining load exceeds a threshold value, how to notify the user of the event is specifically disclosed. Not.
Further, in the machining load monitoring method disclosed in Patent Document 1, for example, only the machining load estimated by the observer for estimating the disturbance load torque is monitored, and the observation of other physical quantities is not disclosed. .. Further, for example, regarding the period for calculating statistical values such as average and variance, for example, conditions indicating the wear state of the tool (for example, cumulative use time of the tool, number of times of use of the tool, cumulative actual cutting time of the tool, etc. Statistical values are calculated uniformly regardless of the condition).

Japanese Unexamined Patent Publication No. 7-132440

For example, when the same machining step is repeatedly performed on a plurality of workpieces, it is desired to be able to determine whether or not a machining abnormality has occurred in each machining step by a method suitable for each machining state.

(1) The abnormality detection device according to one aspect of the present disclosure detects an abnormality in a machining command consisting of one or more machining steps executed in the control device, so that the abnormality detection device is executed at a predetermined time interval when the machining command is executed. The machining state collecting unit that collects the acquired physical quantity indicating the machining state in the machining step as the machining execution information of the machining step together with the time information when the physical quantity is acquired, and the machining that is collected by the machining state collecting section. The machining execution information recording unit that records the execution information in the storage unit and the machining step that is the same as the machining step are executed a plurality of times for any one of the machining steps, and the machining steps recorded in the storage section are recorded a plurality of times. From a set of machining execution information of the same machining step as the machining step, the machining step suitable for calculating an average pattern which is a time change of an average physical quantity of the machining execution information of any one of the machining steps. An average of the machining execution information of any one of the machining steps based on a selection unit that selects a subset of machining execution information of the same machining step and a subset of the machining execution information selected by the selection unit. The average pattern calculation unit that calculates a pattern and the target processing execution information that is the processing execution information of the processing step acquired by executing the arbitrary one processing step are calculated by the average pattern calculation unit. An abnormality detection unit for detecting an abnormality during execution of the arbitrary one processing step as compared with an average pattern is provided.

(2) The abnormality detection server according to one aspect of the present disclosure includes the abnormality detection device according to (1), and is communicated with the control device.

(3) In the abnormality detection method according to one aspect of the present disclosure, in order to detect an abnormality in a machining command consisting of one or more machining steps executed in a control device, an abnormality is detected at a predetermined time interval when the machining command is executed. A machining state collection step that collects the acquired physical quantity indicating the machining state in the machining step as machining execution information of the machining step together with the time information when the physical quantity is acquired, and a machining execution that is collected in the machining state collection step. The processing execution information recording step of recording information in the storage unit and the processing of the same processing step as the processing step are executed a plurality of times for any one processing step, and the processing is recorded a plurality of times in the storage unit. Same as the machining step suitable for calculating an average pattern which is a time change of an average physical quantity of the machining execution information of any one of the machining steps from a set of machining execution information of the same machining step as the step. Based on the selection step that selects a subset of the machining execution information of the machining step and the subset of the machining execution information selected in the selection step, an average pattern of the machining execution information of the arbitrary one of the machining steps. The average pattern calculation step for calculating the above and the target machining execution information which is the machining execution information of the machining step acquired by executing the arbitrary one machining step, and the average calculated in the average pattern calculation step. A computer executes an abnormality detection step of detecting an abnormality at the time of executing the arbitrary one processing step as compared with the pattern.

According to one aspect, for example, when the same machining step is repeatedly performed on a plurality of workpieces, it is possible to determine whether or not a machining abnormality has occurred in each machining step by a method suitable for each machining state. Anomaly detection devices can be provided.

It is a block diagram which shows the hardware configuration of the main part of the abnormality detection apparatus which concerns on one Embodiment. It is a block diagram which shows the functional structure of the numerical control apparatus which concerns on one Embodiment. It is a figure which shows the example of the content included in the processing step which concerns on one Embodiment. It is a figure which shows the example of the content included in the processing execution information which concerns on one Embodiment. It is a figure which shows an example of the processing state table which concerns on one Embodiment. It is a figure which shows an example of the processing state table which concerns on one Embodiment. It is a figure which shows the outline which calculates the average pattern using a plurality of physical quantities and processing time for the same processing step which concerns on one Embodiment. It is a figure which shows the outline which calculates the average pattern using a plurality of physical quantities and a machining time which satisfy the condition concerning a predetermined cumulative tool use time for the same machining step which concerns on one Embodiment. It is a figure which shows the example which detects whether or not an abnormality has occurred in the processing step during processing, and displays the detection result as a graph in real time. It is a figure which shows the example which graphically displays the analysis whether or not there was an abnormality in a machining step after machining. It is a flowchart which shows the operation of the abnormality detection apparatus at the time of detecting whether or not the abnormality occurred in the processing step during execution of the processing step included in the processing command, and displaying the detection result as a graph in real time. It is a flowchart which shows the operation of the abnormality detection apparatus in the case of performing the performance analysis whether or not there was an abnormality in each processing step included in the processing command after executing a processing command.

Hereinafter, an example of the embodiment of the present invention will be described. In the present embodiment, the numerical control device 1 is exemplified as the control device 1 of the machine tool. The machine tool is, for example, a 5-axis machine tool, but is not limited to this. For example, a 3-axis machine may be used.
Further, in the present embodiment, the case where the machine tool is a cutting machine or a grinding machine is illustrated, but the present invention is not limited to this. If the machine tool is an electric discharge machine, for example, a physical quantity related to applied voltage or current, if it is a laser machine tool or a water jet machine, for example, a physical quantity related to laser output or water pressure, if it is an injection molding machine, for example. By using the physical quantity related to the heating temperature or the injection pressure as the machining execution information described later in each machine tool, it is possible to similarly detect whether or not an abnormality has occurred during the execution of any one machining step. ..

The system according to the present embodiment includes a numerical control device 1 and an abnormality detection device 2 as shown in FIG. The abnormality detection device 2 is a numerical control device 1 that executes a machining command composed of one or a plurality of machining steps, and determines whether or not an abnormality has occurred during execution of any one machining step after or during machining. It is to detect. As shown in FIG. 1, the numerical control device 1 and the abnormality detection device 2 are interconnected. Here, as an interconnection method, the abnormality detection device 2 may be directly connected to the numerical control device 1 via an interface unit (not shown). Further, the abnormality detection device 2 may be connected to the numerical control device 1 via a network, for example. Alternatively, the abnormality detection device 2 may be included in the numerical control device 1. Alternatively, the numerical control device 1 may include a part of the functional blocks described later included in the abnormality detection device 2.
Before explaining the abnormality detection device 2, the numerical control device 1 will be described.

FIG. 2 is a block diagram showing a hardware configuration of a main part of the numerical control device 1 according to the present embodiment.
In the numerical control device 1, the CPU 11 as a control unit is a processor that controls the entire numerical control device 1. The CPU 11 reads a system program stored in the ROM 12 as a storage unit via the bus 20, and controls the entire numerical control device 1 according to the system program.
The RAM 13 as a storage unit stores temporary calculation data, display data, and various data input by the operator via the display / MDI unit 70. Further, since the access to the RAM is generally faster than the access to the ROM, the CPU 11 expands the system program stored in the ROM 12 on the RAM 13 in advance, reads the system program from the RAM 13, and executes the system program. May be good.
The non-volatile memory 14 as a storage unit is a magnetic storage device, a flash memory, an MRAM, an FRAM (registered trademark), an EEPROM, a SRAM or a DRAM backed by a battery, or the like, and the power of the numerical control device 1 is turned off. Is also configured as a non-volatile memory that holds the storage state. The non-volatile memory 14 stores a machining program or the like input via the interface 15, the display / MDI unit 70, or the communication unit 27.

Various system programs for executing the processing of the editing mode required for creating and editing the machining program and the processing for automatic operation are written in the ROM 12 in advance.
Various machining programs are input via the interface 15, the display / MDI unit 70, or the communication unit 27, and are stored in the non-volatile memory 14.
The ROM 12, RAM 13, and non-volatile memory 14 are also referred to as storage units.
The interface 15 connects the numerical control device 1 and the external device 72. From the external device 72, the machining program, various parameters, and the like are read into the numerical control device 1. Further, the machining program edited in the numerical control device 1 can be stored in the external storage means via the external device 72. Specific examples of the interface 15 include RS232C, USB, SATA, PC card slot, CF card slot, SD card slot, Ethernet (registered trademark), Wi-Fi, and the like. The interface 15 may be present on the display / MDI unit 70. Examples of the external device 72 include a computer, a USB memory, a CFast, a CF card, an SD card, and the like.

The PMC (Programmable Machine Controller) 16 uses a sequence program built in the numerical control device 1 to add an I / O unit 17 to an auxiliary device of a machine tool (for example, an automatic tool changer including an actuator such as a robot hand for changing tools). The signal is output and controlled via. Further, the PMC 16 receives signals from various switches of the operation panel 71 deployed in the main body of the machine tool, performs necessary signal processing, and then passes the signals to the CPU 11. The PMC 16 is also generally referred to as a PLC (Programmable Logical Controller).
The operation panel 71 is connected to the PMC 16. The operation panel 71 may include a manual pulse generator or the like.
The display / MDI unit 70 as a display unit is a manual data input device including a display 701 and an operation unit such as a keyboard or a touch panel 702. The interface 18 sends screen data for display to the display 701 of the display / MDI unit 70, and also receives commands and data from the operation unit of the display / MDI unit 70 and passes them to the CPU 11.

The axis control circuits 30 to 34 of each axis of X, Y, Z, B, and C are composed of a processor, a memory, and the like, and receive a movement command amount of each axis from the CPU 11 and issue a command of each axis to the servo amplifier 40. Output to ~ 44. In response to this command, the servo amplifiers 40 to 44 drive the servomotors 50 to 54 of the X, Y, Z, B, and C axes. The servomotors 50 to 54 of each axis have a built-in pulse encoder for position detection, and the position signal from the pulse encoder is fed back as a pulse train. A linear scale may be used as the position detector. Further, a velocity feedback signal can be generated by F / V (frequency / velocity) conversion of this pulse train. Then, by feeding back the position / speed feedback signal to the axis control circuits 30 to 34, the position / speed feedback control is performed by the processor.

The spindle control circuit (also referred to as "spindle control circuit") 60 is also composed of a processor, memory, etc., receives a spindle rotation command from the CPU 11, and sends a spindle speed signal ("spindle speed") to the spindle amplifier (also referred to as "spindle amplifier") 61. Also called "signal") is output. The spindle amplifier 61 receives the spindle speed signal and rotates the spindle motor (also referred to as "spindle motor") 62 at the commanded rotation speed to drive the tool.
A pulse encoder is coupled to the spindle motor 62 by a gear or a belt, the pulse encoder 63 feeds back a feedback pulse to the spindle control circuit 60 in synchronization with the rotation of the spindle, and the processor of the spindle control circuit 60 performs speed control processing. Do.

The abnormality detection device 2 is a numerical control device 1 that executes a machining command composed of one or a plurality of machining steps a plurality of times, and determines whether or not an abnormality has occurred during execution of any one machining step after machining or machining. Detect inside. Hereinafter, any one machining step that is a target for detecting whether or not an abnormality has occurred is also referred to as a “machining step for abnormality detection” or a “machining step for analysis”.
Therefore, in the arbitrary machining step included in the machining command executed by the numerical control device 1, the abnormality detection device 2 sets the physical quantity and the time information, which are the machining execution information acquired by the sensing means, into the machining step. From the set of machining execution information collected for each machining step by collecting, for example, the machining execution information acquired in the machining step of the same machining shape and the same machining method as the function to be linked and collected. A function to select the optimum subset and calculate the average pattern, which is the time change of the average physical quantity for determining the presence or absence of an abnormality in the machining step of the abnormality detection target, and the machining execution information in the machining step of the abnormality detection target. A function of comparing with the average pattern of the machining step, a function of detecting whether or not the comparison result deviates from a predetermined threshold or more, and when the comparison result deviates from a predetermined threshold or more, in the machining step. It is provided with an abnormality detection function including a function of determining that a processing abnormality has occurred and a function of identifying and displaying a divergent area when it is determined that an abnormality has occurred. The details of the abnormality detection function will be described later.

Before explaining the abnormality detection function, the machining shape, the machining command, the machining step, and the machining execution information in the present embodiment will be described.

The processed shape refers to a shape after processing of a work piece (also referred to as a “work”) designed by a user using CAD (Computer-Aided Design), for example.

The machining command refers to machining command information for machining a workpiece into a machining shape, which is created by a user using CAM (Computer-Aided Manufacturing) from, for example, machining shape data designed by CAD. The machining command includes, for example, setting of machining contents such as machining shape, cutting conditions, strategy, approach method, retract method, and the like. Specifically, as will be described later, the machining command provides information on a single or a plurality of machining steps (from the first machining step to the first machining step) when the unit for machining one type of machining shape with one type of tool is a machining step. N (N is an arbitrary natural number) Information up to the machining step) is included.

FIG. 3A is a diagram showing an example of information related to the processing content included in the processing step. As described above, the machining step is a unit for machining one type of machining shape with one type of tool. With reference to FIG. 3A, the machining step includes, for example, a machining step number, a machining step start date and time, and machining. Setting of machining contents such as step end date and time, tool number, machining shape, machining features, material of workpiece, cutting conditions, machining method (for example, approach method and retract method), CAM tolerance, surface roughness, geometrical tolerance, and Processing request information including dimensional tolerances, etc. are included. The information related to the processing content is not limited to these. For example, the information related to the machining content may include information such as the spindle speed, the cutting feed rate, the feed amount per blade, the cutting depth, the cutting width, and the tool path.
In this way, the machining command is composed of one or a plurality of machining steps, and the machining shape and the machining method are described in each machining step, and the numerical control device 1 works by executing the machining command. The machine can be made to perform processing.

FIG. 3B is a diagram showing an example of data included in the machining execution information. With reference to FIG. 3B, the machining execution information includes, for example, machining command information, machine tool number, machining command start date and time, machining command end date and time, and the like. In addition, the machining state at the time of machining based on the machining command, which is acquired (or measured) at a predetermined sampling time each time the machining command is executed by the machine tool by the numerical control device 1 for each machining step, and the machining state thereof. Includes time and time information.
Specifically, the machining execution information includes information related to the machining state in the machine tool obtained when the machining command is executed by the numerical control device 1, such as servo information, various sensor data information, resource information (tool usage time, etc.) and the like. ..
Machining execution information can be associated with each machining step in which one type of machining shape is machined with one type of tool. By doing so, it is possible to associate the same number of machining execution information as the number of times the same machining command is executed with the same machining step (that is, the machining step of machining the same machining shape with the same tool). As described above, since the state at the time of machining execution is acquired at a predetermined sampling cycle, the machining execution information of the same machining step is obtained at the time of machining execution at each sampling time from the start time to the end time of the machining step. Statistical processing can be performed based on the state of.
The abnormality detection device 2 according to the present embodiment sets the abnormality detection target from the plurality of processing execution information associated with each execution when one processing step is executed a plurality of times acquired as described above. An appropriate subset is selected based on the machining step, for example, an average pattern of the machining step is calculated, and this average pattern and the machining step obtained when the machining step to be anomaly detected is executed. It is assumed that the processing execution information is compared with.
Therefore, the average pattern of machining steps calculated by the abnormality detection device 2 is not fixed. For example, when the machining command is executed a plurality of times, the machining step included in the machining command is also executed a plurality of times. In this case, the average pattern (i) calculated when the machining step (i) executed at the i-th time (i> 1) is set as the abnormality detection target and the machining step (i) executed at the j-th time (j> i) ( The average pattern (j) calculated when j) is set as an abnormality detection target does not necessarily have the same value.

<Processing execution information>
Next, an example of processing execution information in this embodiment will be described. In the following, as the physical quantities included in the machining execution information, the spindle load meter value, the spindle torque value, each axis servo torque value, each axis servo position, and the resource information (tool usage time) acquired by the sensing means are used. Etc.) are illustrated.

The spindle load meter value is, for example, the maximum output reference load meter value obtained by dividing the output at a certain motor speed during operation of a machine tool by the maximum output when the maximum current is supplied to the motor, and / or the motor is output for an infinite time. The continuous rated output reference load meter value divided by the possible continuous rated output may be measured.

As the spindle torque value, for example, by incorporating a disturbance estimation observer (not shown) in the spindle control circuit 60, the spindle torque applied to the spindle motor 62 can be measured. The measurement of the spindle torque is not limited to this. For example, the spindle torque applied to the spindle motor 62 may be measured by the drive current flowing through the spindle motor 62. Further, a torque sensor may be specially added to measure the spindle torque.

Similarly, for each axis servo torque value (each axis servo torque (each axis load torque) applied to the X, Y, Z axis servo motors 50 to 52 of the tool feed axis), the tool feed axis X, Y, Z By incorporating a disturbance estimation observer (not shown) into the shaft control circuits 30 to 32 that drive and control the shaft servomotors 50 to 52, each shaft servo torque (load torque) applied to each servomotor 50 to 52 by this observer. Can be measured. The drive current of each of the X, Y, and Z axis servomotors of the tool feed shaft may be measured, and the servo torque of each axis may be estimated from this drive current. Further, a torque sensor may be added to measure the servo torque (load torque) of each shaft applied to the servo motor of each shaft.

The servo position information of each axis may be measured by, for example, a position feedback signal from a pulse encoder built in the servomotors 50 to 52 of each axis.

Further, as the resource information (tool usage time, etc.) at the time of machining, the tool information used and the tool usage time may be measured for each machining step.

<Abnormality detection function>
Next, the abnormality detection function provided in the abnormality detection device 2 will be described.
The abnormality detection device 2 may include a control unit 21 and a storage unit 22, and may further include various input / output and communication devices.

The control unit 21 is a part that controls the entire abnormality detection device 2, and realizes various functions in the present embodiment by reading and executing software (abnormality detection program) stored in the storage unit 22, for example. The control unit 21 may be a CPU.
Further, the control unit 21 includes a processing state collecting unit 211, a processing execution information recording unit 212, a selection unit 213, an average pattern calculation unit 214, an abnormality detection unit 215, and an output unit 216.

The storage unit 22 is a storage area for various programs and various data for making the hardware group function as the abnormality detection device 2, and may be a ROM, RAM, flash memory, hard disk drive (HDD), or the like.
FIG. 1 is a block diagram showing a functional configuration of the control unit 11. Referring to FIG. 1, the control unit 21 includes a machining state collecting section 211, a machining execution information recording section 212, a selection section 213, an average pattern calculation section 214, an abnormality detection section 215, and an output section 216. When a machining abnormality is detected from the machining execution information measured during the machining step of the abnormality detection target by each of these functional units, the user can easily grasp the time and / or location where the machining abnormality is detected. Is possible.

<Processing state collection unit 211>
When the numerical control device 1 executes each one or more machining steps included in the machining command, the machining state collecting unit 211 acquires the machining state in each machining step at a predetermined time interval (sampling time) by, for example, a sensing means. (For example, the above-mentioned spindle load meter value, spindle torque value, each axis servo torque value, each axis servo position, etc.) are collected together with the acquired time information (sampling time) as machining execution information of the machining step. To do.
The machining state collecting unit 111 may further acquire resource information (for example, the tool number of the above-mentioned tool and the tool usage time of the tool) in each machining step as machining execution information.

<Processing execution information recording unit 212>
The machining execution information recording unit 212 records the machining execution information collected by the machining state collecting unit 111 for each machining step in the storage unit 22 in association with, for example, the machining step number of the machining step. It should be noted that management information indicating the number of times the processing step is executed may be recorded, for example. Alternatively, the date and time information when the machining step is executed may be recorded.
The machining execution information recording unit 212 can further record the tool number of the tool used in each machining step and the usage time of the tool in the storage unit 22 in association with the machining step number Cn of the machining step. Note that resource usage information indicating the tool usage status (tool is in use or tool is not in use) may be appropriately recorded (for example, at each sampling time). By doing so, for example, the cumulative tool usage time of the tool used for the machining step can be recorded.
As will be described later, instead of the cumulative tool machining time, for example, the cumulative cutting energy, the cumulative actual cutting time, the cutting load, the wear state of the tool, the number of times the tool is used, etc. are recorded as the machining execution information. You may.

4A and 4B are diagrams showing an example of a machining state table for recording machining execution information. Here, one physical quantity at each sampling time Tn (i) (1 ≦ i ≦ M) of each machining step Cn including one or more (N) machining steps Cn (1 ≦ n ≦ N). Is Dn (i) and the tool usage state On (i), and as shown in FIG. 4A, the samples are collected at each sampling time Tn (i) corresponding to one machining step Cn (1 ≦ n ≦ N). , The physical quantity Dn (i) indicating the machining state, and the resource usage information On (i) indicating the tool usage state can be recorded in the storage unit 22, for example, in a table format.

Further, the machining execution information recording unit 212 executes the machining command a plurality of times (K times: 1 <K) (for example, when the machining command is executed, the machining step is executed once). It is possible to associate K machining execution information with the same machining step Cn.
More specifically, the machining execution information Cn (j) of the machining step Cn collected by executing the machining command at the jth time (1 ≦ j ≦ K) is obtained at each sampling time Tn as shown in FIG. 4B. (I) One physical quantity in (1 ≦ i ≦ M) can be expressed as Dn (i, j) and the tool usage state On (i, j).
As described above, when the machining command is executed a plurality of times, the machining step included in the machining command is executed a plurality of times, and each time the machining step is executed, the storage unit 22 stores the machining execution information related to the machining step. However, a plurality of them are recorded in the order in which they are executed. In this way, a plurality of machining execution information related to the same machining step is stored in the storage unit 22 in the order of execution.

<Selection unit 213>
The abnormality detection device 2 evaluates the processing step by the average pattern calculation unit 214, which will be described later, in order to detect whether or not an abnormality has occurred at the time of executing the processing step (analysis target processing step) to be detected. Calculate the average pattern that serves as a reference for doing this.
Therefore, the selection unit 213 executes the machining related to the machining step from a set of a plurality of machining execution information related to the machining step recorded in the storage unit 22 in the order of execution, based on preset filtering conditions. Select a subset of information.
Specifically, as a subset of machining execution information, filtering conditions can be set so that similar machining conditions such as machining conditions and / or machining states when executing the machining target machining step to be analyzed are selected. ..
For example, as a filtering condition, a condition for selecting a predetermined number of machining execution information related to the machining step executed most recently of the machining step to be analyzed may be set.
Further, as a filtering condition, the range of the cumulative tool time is set to the analysis target machining step so that the cumulative tool usage time related to the tool used in each machining step is similar to the state of the tool when machining the analysis target machining step. It may be set corresponding to.
In addition, instead of the range of the cumulative tool usage time, as described above, filtering conditions are set based on, for example, the cumulative cutting energy amount, the cumulative actual cutting time, the cutting load, the tool wear state, the number of times the tool is used, and the like. You may try to do it.
Further, when selecting a subset of the machining execution information related to the machining step from a set of a plurality of machining execution information related to the machining step recorded in the storage unit 22 in the order of execution, the subset is included in the subset. Further, the machining step in which an abnormality is detected may be excluded from the machining step.

FIG. 5 is a diagram showing a case of selecting a subset consisting of machining execution information of a machining step executed most recently of the machining step to be analyzed. Here, for example, a case where the machining step is executed once every day is illustrated. For example, when the analysis target machining step is executed (or executed) on March 6, 2019, the selection unit 213 performs the latest 5 cases (specifically, from March 1) of the analysis target machining step execution. The filtering condition is set so as to select the processing execution information) executed on March 5 and recorded in the storage unit 22.

FIG. 6 shows a machining step executed most recently of the machining step to be analyzed, and filtering conditions are set so as to select a subset that satisfies the condition that the cumulative tool usage time is within the range of 4 minutes ± 3 minutes. It is a figure which illustrates the case. In this case, since the cumulative tool usage time increases each time the machining step is executed, the filtering condition is set so as to be similar to the cumulative tool usage time in the machining target machining step.
In this way, the selection unit 213 can select a subset consisting of appropriate machining execution information based on preset filtering conditions in response to the machining target machining step to be analyzed. By doing so, the average pattern calculation unit 214, which will be described later, can calculate an appropriate average pattern in order to detect whether or not an abnormality has occurred in the processing step to be analyzed. Further, by appropriately setting the filtering conditions, the average pattern calculation unit 214, which will be described later, can create an average pattern according to the case. Further, the abnormality detection unit 215, which will be described later, can perform comparison accuracy based on the characteristics of the processing.

<Average pattern calculation unit 214>
As described above, has the average pattern calculation unit 214 generated an abnormality during execution of the analysis target processing step based on the subset of processing execution information selected by the selection unit 213 according to the analysis target processing step? Calculate the average pattern that serves as a reference for detecting whether or not.
Specifically, the average pattern calculation unit 214 calculates the average value of the physical quantities from the plurality of processing execution information selected by the selection unit 213 for each same sampling cycle in which the processing execution information is collected. You may. Then, the average pattern calculation unit 214 has, for example, plus X percent (X is a preset number) and minus Y percent (Y is a preset number) with respect to the average value calculated for each same sampling cycle. The average pattern may be calculated with the range of. Further, specific upper limit values and lower limit values may be set corresponding to each sampling cycle.
FIGS. 5 and 6 exemplify an average pattern in which a permissible range is set with a 25% increase in the average value as the upper limit and a 25% decrease in the mean value as the lower limit for each sampling cycle.
The method of setting the allowable range is not limited to the above-mentioned example. For example, the range may be set by using the variance in each sampling period. In addition, the average pattern (particularly the allowable range) may be calculated based on an arbitrary statistical method.
As described above, the average pattern calculation unit 214 can calculate an appropriate average pattern according to the processing step to be analyzed. Therefore, the abnormality detection unit 215, which will be described later, can improve the accuracy of detecting whether or not an abnormality has occurred in the analysis target processing step.

<Anomaly detection unit 215>
When the abnormality detection unit 215 newly executes the machining command by the numerical control device 1, the physical quantity and the average pattern collected at a predetermined time interval (sampling time) in the analysis target machining step included in the machining command. By comparing the average pattern calculated by the calculation unit 214 according to the analysis target processing step for each same sampling time, the presence or absence of a deviation of a predetermined threshold value or more set in advance (that is, the analysis target processing step). Whether the collected physical quantity stays within the permissible range or exists outside the permissible range at each sampling time) can be detected.

The output unit 216, which will be described later, inputs a threshold value as a permissible range into the average pattern calculated by the average pattern calculation unit 214 by inputting a ratio or a value, and as shown in FIGS. 5 and 6, sampling of the processing step to be analyzed. The permissible range of the average pattern can be highlighted as a boundary indicating the occurrence of an abnormality in the processing step to be analyzed with respect to the physical quantity indicating the processing state at the time. By doing so, the abnormality detection unit 215 can intuitively grasp on the graph that the physical quantity exceeds the permissible range via the output unit 216, which will be described later, when an abnormality is detected in the analysis target processing step. Can be highlighted as such.

<Real-time processing for detecting abnormalities during machining>
The abnormality detection unit 215 determines the physical quantity at the sampling time of the analysis target machining step collected during the execution of any analysis target machining step included in the machining command while the machining command is being executed by the numerical control device 1. The average pattern calculation unit 214 can detect whether the average pattern calculated according to the analysis target machining step remains within the permissible range at the sampling time or exists outside the permissible range. That is, the abnormality detection unit 215 detects whether or not the physical quantity indicating the machining state at the sampling time of the analysis target machining step deviates from or more than a predetermined threshold value at the preset sampling time. To do.
When the abnormality detection unit 215 detects the deviation, it determines that the processing abnormality has occurred in the analysis target processing step, and highlights the area where the processing abnormality has occurred in real time via the output unit 216 described later. By doing so, it is possible to notify the user of a machining abnormality in any analysis target machining step included in the machining command while the machining command is being executed by the numerical control device 1.
As a result, the user can, for example, determine the machining abnormality of the current machining in real time during machining, interrupt the machining, reduce the load by lowering the cutting speed, and perform processing such as tool replacement as necessary. It can be carried out.

<Abnormality detection batch processing after processing>
After the machining command is executed by the numerical control device 1, the abnormality detection unit 215 averages the physical quantities of the analysis target machining information collected during the execution of any analysis target machining step included in the machining command at each sampling time. The pattern calculation unit 214 can detect whether or not the average pattern calculated according to the analysis target machining step remains within the permissible range at the sampling time.
When the abnormality detection unit 215 detects a deviation, it determines that a processing abnormality has occurred in the analysis target processing step, and highlights an area exceeding the permissible range via the output unit 216 described later. Therefore, it is possible to collectively notify the user of the abnormal parts generated in the analysis target machining step after executing the machining command.
By doing so, after executing the machining command, the user can, for example, confirm that there is no abnormality in the machining record, or collectively investigate the abnormal points generated in the analysis target machining step. As a result, the user can use it for finding a problem in the machining command and improving the machining command.

<Output unit 216>
As shown in FIG. 5 or 6, the output unit 216 displays, for example, the average pattern (that is, the average value and the region of the allowable range) calculated by the average pattern calculation unit 214 according to the processing step to be analyzed. Display on. As described above, the threshold value for setting the permissible range is given by a ratio (% or the like), a real number (value) or the like.
The output unit 216 is displayed so as to be superimposed on the area of the average pattern displayed on the display 70 for each sampling time in the analysis target machining step included in the machining command and calculated according to the analysis target machining step. be able to.
Hereinafter, the abnormality detection real-time display processing during processing and the abnormality detection display processing after processing will be described.

<Real-time display processing for detecting abnormalities during machining>
As described above, the output unit 216 outputs an average pattern (that is, an average value and an allowable range region) calculated according to the analysis target machining step during execution of any analysis target machining step included in the machining command. For example, it is displayed on the display 70. The output unit 216 plots a physical quantity indicating a processing state related to the processing at regular time intervals (for example, sampling time). The output unit 216 determines whether or not the physical quantity indicating the processing state related to the processing is out of the permissible range in the average pattern calculated according to the analysis target processing step (that is, whether or not there is a deviation of a predetermined threshold value or more). Whether or not is occurring) is displayed in real time.
When the abnormality detection unit 215 detects the deviation, the output unit 216 highlights the area where the deviation has occurred in real time. For example, the output unit 216 can notify the user of a processing abnormality by an alarm to the user, highlighting by changing the color of the graph, sound, forced stop of the machine, or the like.

FIG. 7A shows an example in which when the abnormality detection unit 215 detects a deviation in the spindle load meter value while executing an arbitrary analysis target machining step, the dissociated region is identified and displayed on the display 70 in real time. It is a figure which shows.
As shown in FIG. 7A, while executing an arbitrary analysis target machining step, the current machining state with respect to the average pattern calculated according to the analysis target machining step displayed on the display 70 and its allowable range. The physical quantity indicating is plotted at the sampling time at regular time intervals. Here, the threshold value indicating the permissible range at each sampling time may be given by, for example, a ratio (% or the like) to the average value at each sampling time or a real value (value).
Then, as shown in FIG. 7A, when the permissible range is out of range, the out-of-tolerance range is highlighted in real time, so that the user can easily perform the machining of the current machining (that is, the machining target machining step). The occurrence of an abnormality can be recognized.
As a result, the user can, for example, reduce the load by interrupting the machining or reducing the cutting speed in real time during machining, and perform processing such as tool replacement as necessary.
In addition, as an example of notifying the user that a processing abnormality has occurred when the output unit 216 is out of the allowable range described above, there is a case where the area out of the allowable range is highlighted on the display 70. Although illustrated, it is not limited to this.
For example, the output unit 216 may notify the user that a processing abnormality has occurred by an alarm to the user, highlighting such as a color change of the graph, sound, forced stop of the machine, or the like.

<Abnormality detection display processing after processing>
As described above, the abnormality detection unit 215 indicates the machining state related to the machining process at all sampling times of any analysis target machining step included in the machining command after the machining command is executed by the numerical control device 1. It is possible to detect whether or not the physical quantity remains within the permissible range at the sampling time in the average pattern calculated according to the processing step to be analyzed.
When the abnormality detection unit 215 detects the deviation, the abnormality detection unit 215 highlights the area exceeding the permissible range in the analysis target processing step on the output unit 216, so that the user is informed after the processing command is executed. It is possible to collectively notify the abnormal parts generated in any analysis target processing step.

FIG. 7B is a diagram showing an example in which a region in which a deviation is detected with respect to the spindle load meter value is identified and displayed on the display 70 by the abnormality detection unit 215 after the execution of an arbitrary analysis target machining step.
As shown in FIG. 7B, after executing an arbitrary analysis target machining step, the machining step is started with respect to the average pattern calculated according to the analysis target machining step displayed on the display 70 and its allowable range. A physical quantity indicating the processing state from the time to the end is plotted every fixed time (for example, sampling time). Here, as described above, the threshold value indicating the permissible range at each sampling time may be given by, for example, a ratio (% or the like) to the average value at each sampling time or a real value (value).
The output unit 216 provides the user with a region in which the physical quantity indicating the machining state from the start of the machining step to the end of the machining step for each machining step to be analyzed when the machining command is executed exceeds the permissible range. Highlight all together. Specifically, for example, when the graph is out of the permissible range, highlighting such as changing the color of the graph may be performed.
By doing so, it is possible to carry out a cross-sectional investigation and analysis of a region in which the physical quantity indicating the machining state in any analysis target machining step exceeds the permissible range. As a result, it can be used for finding problems related to the processing and improving the processing command.

The configuration of each functional unit of the numerical control device 1 according to the first embodiment illustrated as the present embodiment has been described above.
Next, the operation related to the abnormality detection process of the abnormality detection device 2 will be described. FIG. 8 is a flowchart showing an operation of detecting an abnormality in the machining step in real time while executing an arbitrary analysis target machining step to be detected as an abnormality. FIG. 9 is a flowchart showing an operation of performing an abnormality detection investigation from the start to the end of an arbitrary analysis target machining step to be an abnormality detection target after the execution of the machining command is completed. In the following operation description, it is assumed that the machining execution information related to the machining step executed before the analysis target machining step is recorded in the storage unit 22 by the machining execution information recording unit 212.

First, referring to the flowchart of FIG. 8, while executing an arbitrary analysis target machining step (hereinafter, also referred to as “Cn_target”) included in the machining command, which is an abnormality detection target, the abnormality in the machining step is detected in real time. The processing flow to be detected will be described.
In step S11, the abnormality detection device 2 (selection unit 213) stores the storage unit 22 in order to calculate the average pattern of the analysis target processing step Cn_target (hereinafter, also referred to as “Cn_avage”) when the processing is executed by the numerical control device 1. A subset of machining execution information is selected from a set of recorded machining execution information related to the machining step based on preset filtering conditions.

In step S12, the abnormality detection device 2 (average pattern calculation unit 214) calculates an appropriate average pattern Cn_average for the analysis target machining step Cn_target based on the subset of the selected machining execution information.
Specifically, the average pattern calculation unit 214 is a statistic (for example, average) related to physical quantities at the same sampling time T (i) with respect to the analysis target processing step Cn_target based on a subset of the selected processing execution information. (Value and allowable range) are calculated, and the average pattern Cn_avage of the processing step Cn_taget to be analyzed is created.

In step S13, the numerical control device 1 starts executing the machining command.

In step S14, when the execution of the analysis target processing step Cn_target is started, the abnormality detection device 2 (output unit 216) of the analysis target processing step Cn_taget, for example, as shown in FIG. 7A, in the order of sampling time T (i). The Cn_avage (i) of the average pattern and the threshold area (allowable range) are output in advance.

In step S15, the abnormality detection device 2 (machining state collecting unit 211) indicates a physical quantity indicating the machining state at the sampling time T (i) of the analysis target machining step Cn_target (hereinafter, “analysis target machining execution information Cn_target (i)). ”) Is collected and recorded in the storage unit 22, and the abnormality detection device 2 (output unit 216) is acquired by the processing state collection unit 211 for each sampling time T (i) of the analysis target processing step Cn_target. The analysis target machining execution information Cn_target (i) is output to.

In step S16, the abnormality detection device 2 (abnormality detection unit 215) detects whether or not Cn_target (i) is within the permissible range at the sampling time T (i). Specifically, the abnormality detection device 2 (abnormality detection unit 215) determines whether or not the Cn_target (i) is within the permissible range of the average pattern Cn_avage (i). If it is within the permissible range (if Yes), the process proceeds to step S18. If not (if No), the process proceeds to step S17.

In step S17, the abnormality detection device 2 (output unit 216) emphasizes and outputs the region related to the sampling time T (i). Specifically, for example, as shown in FIG. 7A, highlighting may be performed on the display 70.

In step S18, the control unit 11 determines whether or not the execution of the analysis target machining step Cn_taget is completed. If the execution of the analysis target machining step Cn_target is not completed (in the case of No), the process proceeds to step S15. When the execution of the analysis target machining step Cn_target (i) is completed (in the case of Yes), the process proceeds to step S19.

In step S19, the abnormality detection device 2 determines whether or not the execution of the machining command is completed. If the execution of the machining command is not completed (in the case of No), the process proceeds to step S14. When the execution of the machining command is completed (in the case of Yes), the processing is terminated.
In the above description, the step order is an example and is not limited to this. For example, the calculation of an appropriate average pattern Cn_avarage (i) for the analysis target processing step Cn_target may be performed when the execution of the analysis target processing step Cn_target is started in step S14.
Further, after step S17, the abnormality detecting device 2 may perform processing such as interrupting the machining step or reducing the cutting speed according to an instruction from the user.

As described above, as shown in FIG. 7A, when the allowable range is exceeded, the area outside the allowable range can be highlighted in real time. As a result, the user can easily recognize the occurrence of a machining abnormality in the current machining step. In response to the occurrence of a machining abnormality, the user can, for example, interrupt the machining step, perform processing such as tool replacement as necessary, or reduce the load by reducing the cutting speed.

Next, with reference to the flowchart of FIG. 9, the processing of the abnormality detection function unit in the case of performing performance analysis after executing the machining command will be described.
Before performing the following processing, the processing execution information of the analysis target processing step Cn_taget and the processing execution information related to the processing step Cn executed before the analysis target processing step Cn_target are recorded in the storage unit 22. And.

Referring to FIG. 9, in step S21, the abnormality detection device 2 (selection unit 213) calculates the average pattern Cn_avage of the analysis target machining step Cn_target when executing the machining abnormality investigation in the machining step Cn included in the machining command. Therefore, from a set of a plurality of machining execution information related to the machining step Cn executed before the analysis target machining step Cn_target recorded in the storage unit 22, the machining execution information is obtained based on preset filtering conditions. Select a subset.

In step S22, the abnormality detection device 2 (average pattern calculation unit 214) calculates an appropriate average pattern Cn_avage (i) for the analysis target machining step Cn_target based on the subset of the selected machining execution information.

In step S23, the abnormality detection device 2 (abnormality detection unit 215) inputs (acquires) the analysis target processing execution information Cn_target (i) of the analysis target processing step Cn_taget from the storage unit 22.

In step S24, the anomaly detection device 2 (abnormality detection unit 215) obtains a subset {i: out of the permissible range} of i in which the Cn_target (i) is located outside the permissible range of the average pattern Cn_avage (i).

In step S25, as shown in FIG. 7B, the abnormality detection device 2 (output unit 216) has a range region of the average pattern Cn_target (i) of the analysis target machining step Cn_target (range region of the mean value and the threshold value (upper and lower limits)). Is output, and Cn_target (i) is output.

In step S26, the abnormality detection device 2 (output unit 216) further emphasizes and outputs the {i: out of allowable range} region as shown in FIG. 7B. If {i: out of allowable range} is an empty set, it may be output as no abnormality.
The abnormality detection device 2 (output unit 216) may output as a file. When outputting as a file, it may be output to the display 70 or the like by a reference program for referencing the file.

In step S27, the abnormality detection device 2 determines whether or not the abnormality detection processing of all the analysis target processing steps Cn_target included in the processing command has been completed. If the process is not completed (No), the process proceeds to step S21. When the process is completed (yes), the process is terminated.
As described above, as shown in FIG. 7B, the physical quantity (analysis target machining execution information Cn_taget (i)) indicating the machining state from the start to the end of the analysis target machining step Cn_target included in the machining command after the machining command is executed is obtained. Areas that exceed the permissible range can be highlighted collectively to the user. As a result, it can be used for finding problems related to the processing and improving the processing command.
The operation of the abnormality detection device 2 has been described above.

Each component included in the abnormality detection device 2 can be realized by hardware (including an electronic circuit or the like), software, or a combination thereof. When realized by software, the programs constituting this software are installed in the computer (numerical control device 1). In addition, these programs may be recorded on removable media and distributed to users, or may be distributed by being downloaded to a user's computer via a network. Further, when configured by hardware, some or all of the functions of each component included in the above control device are, for example, an ASIC (Application Specific Integrated Circuit), a gate array, an FPGA (Field Programmable Gate Array), a CPLD. It can be configured by an integrated circuit (IC) such as (Complex Programmable Logical Device).

Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments. Further, the effects described in the present embodiment merely list the most preferable effects arising from the present invention, and the effects according to the present invention are not limited to those described in the present embodiment.

[Modification 1]
In the above-described embodiment, the configuration in which the abnormality detection device 2 includes all the functional units related to the abnormality detection function is illustrated. In this case, as described above, the abnormality detection device 2 may be directly connected to the control device 1 via an interface unit (not shown). Further, it may be a server (abnormality detection server) that is communicated and connected to the control device 1 via a network. For example, the abnormality detection device 2 may be an edge server that is communicably connected to each machine (edge). Further, the abnormality detection device 2 may be realized as a virtual server on the cloud. Further, the functional unit of the abnormality detection device 2 may be provided as a function on the cloud.
Further, the abnormality detection device 2 may be included in the control device 1. Alternatively, the control device 1 may include a functional block included in the abnormality detection device 2.
In addition, some functional units related to the abnormality detection function (machining state collection unit, processing execution information recording unit, selection unit, average pattern calculation unit, abnormality detection unit, and output unit) provided in the abnormality detection device 2 are numerically controlled. It may be the configuration provided in 1. In this case, the numerical control device 1 and the abnormality detection device 2 provided with the remaining functional units may be directly connected via an interface unit (not shown) as described above. Further, it may be connected so as to be communicable via a network.

[Modification 2]
In the above-described embodiment, the average pattern calculation unit 214 is created so as to be proportional to the average value, for example, with plus 25% of the average value as the upper limit threshold value and minus 25% as the lower limit threshold value as the allowable range at each sampling time. The average pattern was illustrated, but it is not limited to this.
For example, the threshold value of the permissible range may be set according to the variance of the physical quantity at each sampling time.

<Effect of this embodiment>
According to this embodiment, for example, the following effects can be obtained.

(1) In order to detect an abnormality in a machining command consisting of one or more machining steps executed by the control device 1, the abnormality detection device 2 is a machining step acquired at a predetermined time interval when the machining command is executed. The processing state collecting unit 211 that collects the physical quantity indicating the processing state in the above as the processing execution information of the processing step together with the time information when the physical quantity is acquired, and the processing execution information collected by the processing state collecting unit 211 in the storage unit 22. The same machining step as the machining step is executed a plurality of times for the machining execution information recording unit 212 to be recorded and any one machining step, and the same machining step as the machining step recorded multiple times in the storage unit 22. From a set of machining execution information of a step, machining execution of the same machining step as the machining step suitable for calculating an average pattern which is a time change of an average physical quantity of the machining execution information of the arbitrary one machining step. An average pattern calculation unit that calculates an average pattern of processing execution information of any one machining step based on a selection unit 213 that selects a subset of information and a subset of processing execution information selected by the selection unit 213. The arbitrary one is compared with 214 and the target machining execution information which is the machining execution information of the machining step acquired by executing the arbitrary one machining step with the average pattern calculated by the average pattern calculation unit 214. An abnormality detection unit 215 for detecting an abnormality during execution of one of the machining steps of the above is provided.
Thereby, for example, when the same machining step is repeatedly performed on a plurality of workpieces, it is possible to easily determine whether or not a machining abnormality has occurred in each machining step by a method suitable for each machining state.

(2) In the abnormality detection device 2 according to (1), the abnormality detection unit 215 compares the target processing execution information with the average pattern, and based on the detection of the presence or absence of a deviation of a threshold value or more set in advance, is arbitrary. Anomalies in one of the machining steps may be detected.
Thereby, for example, when the same machining step is repeatedly performed on a plurality of workpieces, it is possible to easily determine whether or not a machining abnormality has occurred in each machining step by setting a threshold value in advance.

(3) When the abnormality detection unit 215 detects an abnormality in any one machining step in the abnormality detection device 2 according to (1) or (2), the physical quantity at which the abnormality is detected and the time when the physical quantity is acquired. May be provided with an output unit 216 that identifies as an abnormality occurrence region.
Thereby, for example, when the same machining step is repeatedly performed on a plurality of workpieces, it is possible to easily recognize whether or not a machining abnormality has occurred in each machining step, and the physical quantity and time at that time can be easily recognized. ..

(4) In the abnormality detection device 2 according to any one of (1) to (3), while executing any one machining step, the machining execution information collected by the machining state collecting unit 211 is targeted as the target machining execution information. You may try to.
As a result, it is possible to determine in real time whether or not a machining abnormality has occurred during machining, and it is possible to notify the user and interrupt machining.

(5) In the abnormality detection device 2 according to any one of (1) to (3), the machining execution information collected by the machining state collecting unit 211 after executing any one machining step is used as the target machining execution information. You may try to do it.
As a result, since it is possible to investigate abnormal parts of processing by batch processing, for example, after processing, it can be used for finding problems and improving processing commands.

(6) In the abnormality detection device 2 according to any one of (1) to (5), the machining state collecting unit 211 further collects the cumulative tool usage time of the tool used in the machining step, and records the machining execution information. The unit 212 further records the cumulative tool usage time of the tool used in the machining step in the storage unit 22 in association with the machining execution information of the machining step, and the selection unit 213 further records in the storage unit 22 a plurality of times. Among each machining step, the machining execution information of the machining step included in the predetermined range in which the cumulative tool usage time is set may be selected.
Thereby, when creating the average pattern, for example, it is possible to select a machining step having a similar tool usage state in any one machining step and calculate the average pattern.

(7) The abnormality detection server may include the abnormality detection device 2 according to any one of (1) to (6) and communicate with the control device 1.
As a result, by connecting the abnormality detection server to the control device 1 via a high-speed and low-delay network such as 5G, for example, a service provided on the cloud causes a machining abnormality to occur when a machining command is executed. The presence or absence can be easily detected.

(8) The abnormality detection method executed by the computer is acquired at a predetermined time interval when the machining command is executed in order to detect an abnormality in the machining command consisting of one or more machining steps executed by the control device 1. A processing state collection step that collects a physical quantity indicating a processing state in a machining step as processing execution information of the processing step together with a time information obtained by acquiring the physical quantity, and a processing execution information collected in the processing state collection step are stored in a storage unit. The same machining step as the machining step recorded in the storage unit 22 by executing the same machining step multiple times for the machining execution information recording step recorded in 22 and any one machining step. Machining of the same machining step as the machining step suitable for calculating an average pattern which is a time change of an average physical quantity of the machining execution information of the arbitrary one machining step from a set of machining execution information of the machining step. A selection step that selects a subset of execution information, and an average pattern calculation step that calculates an average pattern of machining execution information of any one machining step based on a subset of machining execution information selected in the selection step. And, the target machining execution information which is the machining execution information of the machining step acquired by executing the arbitrary one machining step is compared with the average pattern calculated in the average pattern calculation step, and the arbitrary one is compared. The present invention includes an abnormality detection step for detecting an abnormality during execution of one of the machining steps.
As a result, the same effect as in (1) can be obtained.

1 Numerical control device 2 Abnormality detection device 21 Control unit 22 Storage unit 211 Machining status collection unit 212 Machining execution information recording unit 213 Selection unit 214 Average pattern calculation unit 215 Abnormality detection unit 216 Output unit

Claims (8)

To detect anomalies in a machining command consisting of one or more machining steps executed in a control unit
A machining state collecting unit that collects a physical quantity indicating a machining state in the machining step acquired at a predetermined time interval when the machining command is executed, together with time information obtained by acquiring the physical quantity, as machining execution information of the machining step.
A processing execution information recording unit that records the processing execution information collected by the processing state collecting unit in a storage unit,
For any one of the machining steps, the same machining step as the machining step is executed a plurality of times, and from a set of machining execution information of the same machining step as the machining step recorded multiple times in the storage unit, Selection to select a subset of machining execution information of the same machining step as the machining step suitable for calculating an average pattern that is a time variation of an average physical quantity of the machining execution information of any one of the machining steps. Department and
An average pattern calculation unit that calculates an average pattern of processing execution information of any one of the processing steps based on a subset of the processing execution information selected by the selection unit.
The target machining execution information, which is the machining execution information of the machining step acquired by executing the arbitrary one machining step, is compared with the average pattern calculated by the average pattern calculation unit, and the arbitrary one is compared with the average pattern. An abnormality detection unit that detects an abnormality during execution of one of the machining steps,
Anomaly detection device. The abnormality detection unit compares the target processing execution information with the average pattern, and detects an abnormality in the arbitrary one processing step based on the detection of the presence or absence of a deviation equal to or greater than a preset threshold value. Item 1. The abnormality detection device according to item 1. Claim 1 or claim 1, wherein when the abnormality detection unit detects an abnormality in any one of the processing steps, the abnormality detection unit includes an output unit that identifies the physical quantity at which the abnormality is detected and the time when the physical quantity is acquired as an abnormality occurrence region. The abnormality detection device according to claim 2. The abnormality according to any one of claims 1 to 3, wherein the processing execution information collected by the processing state collecting unit is used as the target processing execution information during the execution of any one of the processing steps. Detection device. The abnormality detection according to any one of claims 1 to 3, wherein the machining execution information collected by the machining state collecting unit is used as the target machining execution information after the execution of any one of the machining steps. apparatus. The machining state collecting unit further collects the tool cumulative usage time of the tool used in the machining step.
The machining execution information recording unit further records the cumulative tool usage time of the tool used in the machining step in the storage unit in association with the machining execution information of the machining step.
The selection unit further selects the processing execution information of the processing step included in the predetermined range in which the cumulative tool usage time is set in advance from each of the processing steps recorded a plurality of times in the storage unit. The abnormality detection device according to any one of claims 1 to 5. An abnormality detection server comprising the abnormality detection device according to any one of claims 1 to 6, which is communication-connected to the control device. To detect anomalies in a machining command consisting of one or more machining steps executed in a control unit
A machining state collection step that collects a physical quantity indicating a machining state in the machining step acquired at a predetermined time interval when the machining command is executed, together with time information obtained by acquiring the physical quantity, as machining execution information of the machining step.
A machining execution information recording step for recording the machining execution information collected in the machining state collecting step in a storage unit,
For any one of the machining steps, the same machining step as the machining step is executed a plurality of times, and from a set of machining execution information of the same machining step as the machining step recorded multiple times in the storage unit, Selection to select a subset of machining execution information of the same machining step as the machining step suitable for calculating an average pattern that is a time variation of an average physical quantity of the machining execution information of any one of the machining steps. Steps and
An average pattern calculation step for calculating an average pattern of machining execution information of any one of the machining steps based on a subset of the machining execution information selected in the selection step.
The target machining execution information, which is the machining execution information of the machining step acquired by executing the arbitrary one machining step, is compared with the average pattern calculated in the average pattern calculation step, and the arbitrary one is compared. An abnormality detection method in which a computer executes an abnormality detection step for detecting an abnormality during execution of one of the machining steps.

Images